Count Every Rotation and Every Rotation Counts: Exploring Drone Dynamics via Propeller Sensing

2025-11-17

AI Summary

This work addresses the challenge of non-contact, real-time perception for unmanned aerial vehicles (UAVs) by proposing a high-precision rotor speed estimation method based on event cameras. To overcome limitations of conventional optical sensors—such as motion blur, low-light sensitivity, and inability to resolve high-speed rotation—we introduce a dual-module framework: “count every rotation” and “every rotation matters,” uniquely leveraging rotor speed as a bridge to jointly infer UAV internal dynamics (e.g., motor states) and external dynamics (e.g., attitude and thrust). Our approach integrates event-stream denoising with an adaptive frequency extraction model, enabling millisecond-level response under complex conditions. Experimental results show a mean latency of only 3 ms, rotor speed estimation error of 0.23%, flight command recognition accuracy of 96.5%, and a 22.3% improvement in trajectory tracking precision. This work establishes a new paradigm for UAV remote monitoring, autonomous obstacle avoidance, and collaborative sensing.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

As drone-based applications proliferate, paramount contactless sensing of airborne drones from the ground becomes indispensable. This work demonstrates concentrating on propeller rotational speed will substantially improve drone sensing performance and proposes an event-camera-based solution, sysname. sysname features two components: extit{Count Every Rotation} achieves accurate, real-time propeller speed estimation by mitigating ultra-high sensitivity of event cameras to environmental noise. extit{Every Rotation Counts} leverages these speeds to infer both internal and external drone dynamics. Extensive evaluations in real-world drone delivery scenarios show that sysname achieves a sensing latency of 3$ms$ and a rotational speed estimation error of merely 0.23%. Additionally, sysname infers drone flight commands with 96.5% precision and improves drone tracking accuracy by over 22% when combined with other sensing modalities. extit{ Demo: {color{blue}https://eventpro25.github.io/EventPro/.} }

Problem

• Accurately estimating drone propeller rotation speeds in real-time
• Inferring both internal dynamics and external flight commands
• Improving drone tracking accuracy through propeller-based sensing

Innovation

• Event camera solution for drone propeller sensing
• Real-time rotational speed estimation with noise mitigation
• Inferring drone dynamics from propeller rotation data